HQNN-CL: Regime-Aware Hybrid Quantum Neural Network with Continual Learning for Financial Forecasting
Organizations: Department of Artificial Intelligence & Data Science, National University of Computer & Emerging Sciences, Islamabad, Pakistan · Department of Computer Science, National University of Computer & Emerging Sciences, Islamabad, Pakistan · Department of Cyber Security, National University of Computer & Emerging Sciences, Islamabad, Pakistan
Abstract
Financial time-series forecasting is still difficult owing to the non-stationary nature of the market, regime changes, and catastrophic forgetting, which makes conventional deep learning models hard to adapt in the long term. To achieve uncertainty-aware robust financial forecasting in the face of changing market conditions, this study proposes a Hybrid Quantum-Classical Neural Network with Continual Learning (HQNN-CL). The proposed framework combines Gaussian Hidden Markov Model (HMM) based regime detection, BiLSTM temporal encoding, adaptive-depth parameterized quantum circuits, Elastic Weight Consolidation (EWC), experience replay, and probabilistic forecasting in a single architecture. The framework was tested on four real-time stock datasets: Microsoft, Systems Limited, Teradata and Tata Consultancy Services, and compared with seven state-of-the-art forecasting models, including recurrent and Transformer-based models. The experimental results show that HQNN-CL has outperformed other methods on the Systems Limited (RMSE = 3.0149) and Teradata (RMSE = 0.8909) datasets and is within 0.32% and 0.40% of the best baseline method for Microsoft and Tata Consultancy Services, respectively. The proposed framework also generates well-calibrated probabilistic forecasts within the range of 89.5% to 96.5% empirical coverage rate, has zero catastrophic forgetting (BWT = 0.0000) for all sequential learning tasks, and consistently shows positive forward transfer. Ablation and statistical significance analyses also validate the performance of adaptive quantum feature learning and continual adaptation under heterogeneous market conditions, regime-wise.
Figures & tables
| Model | RMSE | MAE | MAPE (%) | |
|---|---|---|---|---|
| LSTM | 6.8344 | 4.7096 | 1.083 | 0.9767 |
| RNN | 6.8090 | 4.7233 | 1.086 | 0.9769 |
| GRU | 6.8128 | 4.6981 | 1.080 | 0.9769 |
| PatchTST | 6.8285 | 4.7150 | 1.084 | 0.9767 |
| iTransformer | 6.8548 | 4.7485 | 1.093 | 0.9766 |
| TimesNet | 7.0024 | 4.8683 | 1.119 | 0.9755 |
| Model | RMSE | MAE | MAPE (%) | |
|---|---|---|---|---|
| LSTM | 3.0193 | 2.0616 | 1.669 | 0.9870 |
| RNN | 3.0182 | 2.0616 | 1.669 | 0.9870 |
| GRU | 3.0223 | 2.0610 | 1.668 | 0.9870 |
| PatchTST | 3.0261 | 2.0630 | 1.669 | 0.9869 |
| iTransformer | 3.1322 | 2.1397 | 1.718 | 0.9860 |
| TimesNet | 3.3339 | 2.2917 | 1.821 | 0.9842 |
| Model | RMSE | MAE | MAPE (%) | |
|---|---|---|---|---|
| LSTM | 48.587 | 34.276 | 1.058 | 0.9950 |
| RNN | 48.666 | 34.342 | 1.060 | 0.9950 |
| GRU | 48.753 | 34.456 | 1.064 | 0.9949 |
| PatchTST | 48.275 | 33.973 | 1.047 | 0.9950 |
| iTransformer | 49.634 | 35.576 | 1.108 | 0.9948 |
| TimesNet | 49.386 | 35.533 | 1.099 | 0.9948 |
| Stock | Coverage @95% | CRPS | Calibration |
|---|---|---|---|
| Microsoft | 94.9% | 3.577 | Well-calibrated |
| Systems Limited | 96.5% | 1.556 | Well-calibrated |
| Teradata | 89.5% | 0.382 | Slightly conservative |
| Tata Consultancy | 92.8% | 24.38 | Well-calibrated |
| Stock | BWT | FWT | Plasticity | PSI |
|---|---|---|---|---|
| Microsoft | 0.0000 | +2.722 | 3.219 | 0.238 |
| Systems Limited | 0.0000 | +0.926 | 0.739 | 0.587 |
| Teradata | 0.0000 | +0.451 | 0.884 | 0.538 |
| Tata Consultancy | 0.0000 | +17.420 | 35.470 | 0.028 |
| Component Removed | Microsoft | Systems Ltd. | Teradata | Tata CS |
|---|---|---|---|---|
| HQNN-CL (Full) | 6.8306 | 3.0149 | 0.8909 | 48.468 |
| w/o Adaptive Q Depth | 6.8148 ( –0.23% ) | 3.0146 ( –0.01% ) | 0.8927 (+0.19%) | 48.468 ( 0.00%) |
| w/o Ensemble (1 Seed) | 6.8368 (+0.09%) | 3.0126 ( –0.08% ) | 0.8924 (+0.17%) | 48.140 ( –0.68% ) |
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Time Series Forecasting
Time series forecasting predicts future values from ordered observations using statistical, neural, and probabilistic models to support decisions under uncertainty.
See all 930 papersA Hybrid Quantum Circuit Born Machine Framework for Financial Volatility Forecasting: Quantum-Assisted Training and Classical Inference
Drop-Prior" mechanism during training, the LSTM implicitly distills structured information from the quantum prior. This establishes a pragmatic paradigm of quantum-assisted training with classical-efficient inference", whereby the model retains its quantum-enhanced accuracy even when the quantum module is entirely disabled during deployment. This demonstrates a practical pathway for leveraging quantum computing to enhance classical models without real-time quantum inference latency.